EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Prediction of bacterial protein–compound interactions with only positive samples

Ki-Hwa Kim, Avinash Yaganapu, Sai Kosaraju iD, Aashish Bhatt, Yun Lyna Luo, Sai Phani Parsa, Juyeon Park, Hyun Lee iD, Jun Hyuck Lee, Tae-Jin Oh iD, Mingon Kang iD

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btag067 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Ki-Hwa Kim und 10 weiteren Autor:innen. Beteiligte Einrichtung: Genome-Based BioIT Convergence Institute, Asan, 31460, Republic of Korea. Hauptthemen laut MEDLINE: Bacterial Proteins, Computational Biology. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation Major Research Instrumentation (NSF MRI), Institute of Information & Communications Technology Planning & Evaluation (IITP), Korean government (MSIT).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Prediction of Compound–Protein Interactions (CPI) in bacteria is crucial to advance various pharmaceutical and chemical engineering fields, including biocatalysis, drug discovery, and industrial processing. However, current CPI models cannot be applied for bacterial CPI prediction due to the lack of curated negative interaction samples. Results We propose a novel Positive-Unlabeled (PU) learning framework, named BIN-PU, to address this limitation. BIN-PU generates pseudo positive and negative labels from known positive interaction data, enabling effective training of deep learning models for CPI prediction. We also propose a weighted positive loss function that weights to truly positive samples. We have validated BIN-PU coupled with multiple CPI backbone models, comparing the performance with the existing PU models using bacterial cytochrome P450 (CYP) data. Extensive experiments demonstrate the superiority of BIN-PU over the benchmark models in predicting CPIs with only truly positive samples. Furthermore, we have validated BIN-PU on additional bacterial proteins obtained from literature review, human CYP datasets, and uncurated data for its reproducibility. We have also validated the CPI prediction for the uncurated CYP data with biological and biophysical experiments. BIN-PU represents a significant advancement in CPI prediction for bacterial proteins, opening new possibilities for improving predictive models in related biological interaction tasks. Availability and implementation The source code and data are available at https://github.com/datax-lab/CYP.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Bacterial ProteinsComputational BiologyCytochrome P-450 Enzyme SystemPrediction AlgorithmsDeep LearningHumans

Substanzen

Bacterial ProteinsCytochrome P-450 Enzyme System

Autor:innen und Institutionen

  • Genome-Based BioIT Convergence Institute, Asan, 31460, Republic of Korea.
  • Department of Computer Science, University of Nevada, Las Vegas, Las Vegas, NV, 89154, United States.
  • Department of Computer Science, California State Polytechnic University, Pomona, CA, 91768, United States.
  • Department of Biotechnology and Pharmaceutical Sciences, Western University of Health Sciences, Pomona, CA, 91766, United States.
  • Division of Computer Science and Engineering, Sun Moon University, Asan, 31460, Republic of Korea.
  • Division of Life Sciences, Korea Polar Research Institute, Incheon, 21990, Republic of Korea.

ORCID-Profile: Sai Kosaraju, Hyun Lee, Tae-Jin Oh, Mingon Kang

Förderung

  • National Science Foundation Major Research Instrumentation (NSF MRI)
  • Institute of Information & Communications Technology Planning & Evaluation (IITP)
  • Korean government (MSIT)
  • Bio & Medical Technology Development Program
  • Basic Science Research Program
  • National Research Foundation of Korea (NRF)

Zitieren

APA

Kim, K. H., Yaganapu, A., Kosaraju, S., Bhatt, A., Luo, Y. L., Parsa, S. P., Park, J., Lee, H., Lee, J. H., Oh, T. J., & Kang, M. (2026). Prediction of bacterial protein–compound interactions with only positive samples. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag067

Vancouver

Kim KH, Yaganapu A, Kosaraju S, Bhatt A, Luo YL, Parsa SP, et al. Prediction of bacterial protein–compound interactions with only positive samples. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag067

BibTeX
@article{Kim2026,
  author = {Kim, Ki-Hwa and Yaganapu, Avinash and Kosaraju, Sai and Bhatt, Aashish and Luo, Yun Lyna and Parsa, Sai Phani and Park, Juyeon and Lee, Hyun and Lee, Jun Hyuck and Oh, Tae-Jin and Kang, Mingon},
  title = {Prediction of bacterial protein–compound interactions with only positive samples},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag067}
}
Kostenlos starten →